ClawHub
Back to skill

Security audit

Principle Comparator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only comparison aid that analyzes two user-provided sources and does not include code, installs, external calls, or privileged actions.

Installers should understand that this skill sends any compared content through the configured agent model, which may be cloud-hosted. Use it for deliberate two-source comparison tasks, and avoid letting the stray requires_review.md wording cause file writes unless the user explicitly asks for a file.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The listed invocation examples include generic phrases such as "What do these sources have in common?" and "Which ideas appear in both?" without clear constraints on source type or context. In a markdown skill description, this can make activation overly broad and increase the chance of unintended invocation during ordinary comparison requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.